© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 6-RES-JB
    6. 17348
    Prev
    Next
    INDEX
    Explanations

    descriptions related to the flavor or essence of something

    oai_token-act-pair · gpt-3.5-turbo

    references to the concept of taste in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.hook_resid_pre
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    vernment
    -0.73
     Glob
    -0.66
    etheless
    -0.63
     Lak
    -0.63
     ESA
    -0.63
    doms
    -0.63
     Dawn
    -0.63
    atern
    -0.62
     CST
    -0.62
     Freeman
    -0.62
    POSITIVE LOGITS
     buds
    1.37
     tasting
    0.92
     palate
    0.89
     tastes
    0.87
     taste
    0.87
     juices
    0.81
    oyal
    0.80
     sensations
    0.79
     testers
    0.79
     dehyd
    0.78
    Activations Density 0.026%

    No Known Activations